trained on clip14 and cxrbert
Browse files- README.md +99 -19
- all_results.json +9 -9
- config.json +13 -11
- eval_results.json +5 -5
- heatmap.png +0 -0
- pytorch_model.bin +2 -2
- runs/Jul07_03-20-36_pop-os/events.out.tfevents.1688696444.pop-os.586616.0 +0 -3
- runs/{Jul07_00-39-43_pop-os/events.out.tfevents.1688686792.pop-os.142684.0 → Jul08_01-50-48_pop-os/events.out.tfevents.1688777456.pop-os.224570.0} +2 -2
- runs/{Jul07_00-39-43_pop-os/events.out.tfevents.1688690222.pop-os.142684.1 → Jul08_01-50-48_pop-os/events.out.tfevents.1688822179.pop-os.224570.1} +2 -2
- tokenizer.json +0 -0
- train_results.json +5 -5
- trainer_state.json +1196 -62
- training_args.bin +2 -2
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -2,31 +2,30 @@
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
model-index:
|
| 5 |
-
- name:
|
| 6 |
results: []
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
|
| 12 |
-
#
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss: 0.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
## Intended uses & limitations
|
| 23 |
|
| 24 |
-
|
| 25 |
-
- Image Retrieval
|
| 26 |
|
| 27 |
## Training and evaluation data
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
## Training procedure
|
| 32 |
|
|
@@ -34,24 +33,105 @@ ROCO dataset
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 5e-05
|
| 37 |
-
- train_batch_size:
|
| 38 |
-
- eval_batch_size:
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: cosine
|
| 42 |
- lr_scheduler_warmup_steps: 500
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch | Step
|
| 48 |
-
|
| 49 |
-
|
|
| 50 |
-
|
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
model-index:
|
| 5 |
+
- name: output_8_clip14_cxrbert
|
| 6 |
results: []
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
|
| 12 |
+
# output_8_clip14_cxrbert
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [pretrained_weights/clip14-cxrbert](https://huggingface.co/pretrained_weights/clip14-cxrbert) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.3388
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
| 20 |
+
More information needed
|
| 21 |
|
| 22 |
## Intended uses & limitations
|
| 23 |
|
| 24 |
+
More information needed
|
|
|
|
| 25 |
|
| 26 |
## Training and evaluation data
|
| 27 |
|
| 28 |
+
More information needed
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
|
|
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 24
|
| 37 |
+
- eval_batch_size: 24
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: cosine
|
| 41 |
- lr_scheduler_warmup_steps: 500
|
| 42 |
+
- num_epochs: 8.0
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 0.7951 | 0.09 | 500 | 1.1912 |
|
| 49 |
+
| 0.5887 | 0.18 | 1000 | 0.9833 |
|
| 50 |
+
| 0.5023 | 0.28 | 1500 | 0.8459 |
|
| 51 |
+
| 0.4709 | 0.37 | 2000 | 0.8479 |
|
| 52 |
+
| 0.4484 | 0.46 | 2500 | 0.7667 |
|
| 53 |
+
| 0.4319 | 0.55 | 3000 | 0.8092 |
|
| 54 |
+
| 0.4181 | 0.64 | 3500 | 0.6964 |
|
| 55 |
+
| 0.4107 | 0.73 | 4000 | 0.6463 |
|
| 56 |
+
| 0.3723 | 0.83 | 4500 | 0.7893 |
|
| 57 |
+
| 0.3746 | 0.92 | 5000 | 0.6863 |
|
| 58 |
+
| 0.3667 | 1.01 | 5500 | 0.6910 |
|
| 59 |
+
| 0.3253 | 1.1 | 6000 | 0.6863 |
|
| 60 |
+
| 0.3274 | 1.19 | 6500 | 0.6445 |
|
| 61 |
+
| 0.3065 | 1.28 | 7000 | 0.5908 |
|
| 62 |
+
| 0.2834 | 1.38 | 7500 | 0.6138 |
|
| 63 |
+
| 0.293 | 1.47 | 8000 | 0.6515 |
|
| 64 |
+
| 0.303 | 1.56 | 8500 | 0.5806 |
|
| 65 |
+
| 0.2638 | 1.65 | 9000 | 0.5587 |
|
| 66 |
+
| 0.2593 | 1.74 | 9500 | 0.5216 |
|
| 67 |
+
| 0.2451 | 1.83 | 10000 | 0.5283 |
|
| 68 |
+
| 0.2468 | 1.93 | 10500 | 0.5001 |
|
| 69 |
+
| 0.2295 | 2.02 | 11000 | 0.4975 |
|
| 70 |
+
| 0.1953 | 2.11 | 11500 | 0.4750 |
|
| 71 |
+
| 0.1954 | 2.2 | 12000 | 0.4572 |
|
| 72 |
+
| 0.1737 | 2.29 | 12500 | 0.4731 |
|
| 73 |
+
| 0.175 | 2.38 | 13000 | 0.4526 |
|
| 74 |
+
| 0.1873 | 2.48 | 13500 | 0.4890 |
|
| 75 |
+
| 0.1809 | 2.57 | 14000 | 0.4210 |
|
| 76 |
+
| 0.1711 | 2.66 | 14500 | 0.4197 |
|
| 77 |
+
| 0.1457 | 2.75 | 15000 | 0.3998 |
|
| 78 |
+
| 0.1583 | 2.84 | 15500 | 0.3923 |
|
| 79 |
+
| 0.1579 | 2.94 | 16000 | 0.3823 |
|
| 80 |
+
| 0.1339 | 3.03 | 16500 | 0.3654 |
|
| 81 |
+
| 0.1164 | 3.12 | 17000 | 0.3592 |
|
| 82 |
+
| 0.1217 | 3.21 | 17500 | 0.3641 |
|
| 83 |
+
| 0.119 | 3.3 | 18000 | 0.3553 |
|
| 84 |
+
| 0.1151 | 3.39 | 18500 | 0.3524 |
|
| 85 |
+
| 0.119 | 3.49 | 19000 | 0.3452 |
|
| 86 |
+
| 0.102 | 3.58 | 19500 | 0.3439 |
|
| 87 |
+
| 0.1085 | 3.67 | 20000 | 0.3422 |
|
| 88 |
+
| 0.1142 | 3.76 | 20500 | 0.3396 |
|
| 89 |
+
| 0.1038 | 3.85 | 21000 | 0.3392 |
|
| 90 |
+
| 0.1143 | 3.94 | 21500 | 0.3390 |
|
| 91 |
+
| 0.0983 | 4.04 | 22000 | 0.3390 |
|
| 92 |
+
| 0.0974 | 4.13 | 22500 | 0.3388 |
|
| 93 |
+
| 0.1007 | 4.22 | 23000 | 0.3389 |
|
| 94 |
+
| 0.0903 | 4.31 | 23500 | 0.3396 |
|
| 95 |
+
| 0.095 | 4.4 | 24000 | 0.3394 |
|
| 96 |
+
| 0.0955 | 4.49 | 24500 | 0.3436 |
|
| 97 |
+
| 0.1032 | 4.59 | 25000 | 0.3426 |
|
| 98 |
+
| 0.1037 | 4.68 | 25500 | 0.3485 |
|
| 99 |
+
| 0.103 | 4.77 | 26000 | 0.3547 |
|
| 100 |
+
| 0.0987 | 4.86 | 26500 | 0.3552 |
|
| 101 |
+
| 0.1076 | 4.95 | 27000 | 0.3537 |
|
| 102 |
+
| 0.1134 | 5.04 | 27500 | 0.3549 |
|
| 103 |
+
| 0.1044 | 5.14 | 28000 | 0.3622 |
|
| 104 |
+
| 0.1099 | 5.23 | 28500 | 0.3774 |
|
| 105 |
+
| 0.1129 | 5.32 | 29000 | 0.3872 |
|
| 106 |
+
| 0.1235 | 5.41 | 29500 | 0.3767 |
|
| 107 |
+
| 0.1099 | 5.5 | 30000 | 0.3880 |
|
| 108 |
+
| 0.1331 | 5.6 | 30500 | 0.4181 |
|
| 109 |
+
| 0.134 | 5.69 | 31000 | 0.4090 |
|
| 110 |
+
| 0.142 | 5.78 | 31500 | 0.4045 |
|
| 111 |
+
| 0.1441 | 5.87 | 32000 | 0.4176 |
|
| 112 |
+
| 0.1577 | 5.96 | 32500 | 0.4377 |
|
| 113 |
+
| 0.1539 | 6.05 | 33000 | 0.4327 |
|
| 114 |
+
| 0.1475 | 6.15 | 33500 | 0.4587 |
|
| 115 |
+
| 0.1616 | 6.24 | 34000 | 0.4709 |
|
| 116 |
+
| 0.1671 | 6.33 | 34500 | 0.4920 |
|
| 117 |
+
| 0.1792 | 6.42 | 35000 | 0.4803 |
|
| 118 |
+
| 0.2025 | 6.51 | 35500 | 0.5275 |
|
| 119 |
+
| 0.1823 | 6.6 | 36000 | 0.5115 |
|
| 120 |
+
| 0.2123 | 6.7 | 36500 | 0.4975 |
|
| 121 |
+
| 0.2043 | 6.79 | 37000 | 0.4890 |
|
| 122 |
+
| 0.2086 | 6.88 | 37500 | 0.5374 |
|
| 123 |
+
| 0.2299 | 6.97 | 38000 | 0.5565 |
|
| 124 |
+
| 0.2151 | 7.06 | 38500 | 0.6073 |
|
| 125 |
+
| 0.222 | 7.15 | 39000 | 0.5468 |
|
| 126 |
+
| 0.236 | 7.25 | 39500 | 0.5504 |
|
| 127 |
+
| 0.2031 | 7.34 | 40000 | 0.5549 |
|
| 128 |
+
| 0.2251 | 7.43 | 40500 | 0.5905 |
|
| 129 |
+
| 0.2251 | 7.52 | 41000 | 0.6012 |
|
| 130 |
+
| 0.2464 | 7.61 | 41500 | 0.5931 |
|
| 131 |
+
| 0.2451 | 7.71 | 42000 | 0.6499 |
|
| 132 |
+
| 0.2463 | 7.8 | 42500 | 0.5696 |
|
| 133 |
+
| 0.2385 | 7.89 | 43000 | 0.5360 |
|
| 134 |
+
| 0.2353 | 7.98 | 43500 | 0.5490 |
|
| 135 |
|
| 136 |
|
| 137 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
-
"train_loss": 0.
|
| 8 |
-
"train_runtime":
|
| 9 |
-
"train_samples_per_second":
|
| 10 |
-
"train_steps_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_loss": 0.3388192057609558,
|
| 4 |
+
"eval_runtime": 139.1474,
|
| 5 |
+
"eval_samples_per_second": 58.743,
|
| 6 |
+
"eval_steps_per_second": 2.451,
|
| 7 |
+
"train_loss": 0.21080181559736064,
|
| 8 |
+
"train_runtime": 44575.4239,
|
| 9 |
+
"train_samples_per_second": 11.741,
|
| 10 |
+
"train_steps_per_second": 0.978
|
| 11 |
}
|
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_commit_hash": null,
|
| 3 |
-
"_name_or_path": "pretrained_weights/
|
| 4 |
"architectures": [
|
| 5 |
"VisionTextDualEncoderModel"
|
| 6 |
],
|
|
@@ -8,9 +8,11 @@
|
|
| 8 |
"model_type": "vision-text-dual-encoder",
|
| 9 |
"projection_dim": 512,
|
| 10 |
"text_config": {
|
| 11 |
-
"_name_or_path": "
|
| 12 |
"add_cross_attention": false,
|
| 13 |
-
"architectures":
|
|
|
|
|
|
|
| 14 |
"attention_probs_dropout_prob": 0.1,
|
| 15 |
"bad_words_ids": null,
|
| 16 |
"begin_suppress_tokens": null,
|
|
@@ -84,12 +86,12 @@
|
|
| 84 |
"typical_p": 1.0,
|
| 85 |
"use_bfloat16": false,
|
| 86 |
"use_cache": true,
|
| 87 |
-
"vocab_size":
|
| 88 |
},
|
| 89 |
"torch_dtype": "float32",
|
| 90 |
"transformers_version": null,
|
| 91 |
"vision_config": {
|
| 92 |
-
"_name_or_path": "openai/clip-vit-
|
| 93 |
"add_cross_attention": false,
|
| 94 |
"architectures": null,
|
| 95 |
"attention_dropout": 0.0,
|
|
@@ -110,7 +112,7 @@
|
|
| 110 |
"forced_bos_token_id": null,
|
| 111 |
"forced_eos_token_id": null,
|
| 112 |
"hidden_act": "quick_gelu",
|
| 113 |
-
"hidden_size":
|
| 114 |
"id2label": {
|
| 115 |
"0": "LABEL_0",
|
| 116 |
"1": "LABEL_1"
|
|
@@ -118,7 +120,7 @@
|
|
| 118 |
"image_size": 224,
|
| 119 |
"initializer_factor": 1.0,
|
| 120 |
"initializer_range": 0.02,
|
| 121 |
-
"intermediate_size":
|
| 122 |
"is_decoder": false,
|
| 123 |
"is_encoder_decoder": false,
|
| 124 |
"label2id": {
|
|
@@ -131,20 +133,20 @@
|
|
| 131 |
"min_length": 0,
|
| 132 |
"model_type": "clip_vision_model",
|
| 133 |
"no_repeat_ngram_size": 0,
|
| 134 |
-
"num_attention_heads":
|
| 135 |
"num_beam_groups": 1,
|
| 136 |
"num_beams": 1,
|
| 137 |
"num_channels": 3,
|
| 138 |
-
"num_hidden_layers":
|
| 139 |
"num_return_sequences": 1,
|
| 140 |
"output_attentions": false,
|
| 141 |
"output_hidden_states": false,
|
| 142 |
"output_scores": false,
|
| 143 |
"pad_token_id": null,
|
| 144 |
-
"patch_size":
|
| 145 |
"prefix": null,
|
| 146 |
"problem_type": null,
|
| 147 |
-
"projection_dim":
|
| 148 |
"pruned_heads": {},
|
| 149 |
"remove_invalid_values": false,
|
| 150 |
"repetition_penalty": 1.0,
|
|
|
|
| 1 |
{
|
| 2 |
"_commit_hash": null,
|
| 3 |
+
"_name_or_path": "pretrained_weights/clip14-cxrbert",
|
| 4 |
"architectures": [
|
| 5 |
"VisionTextDualEncoderModel"
|
| 6 |
],
|
|
|
|
| 8 |
"model_type": "vision-text-dual-encoder",
|
| 9 |
"projection_dim": 512,
|
| 10 |
"text_config": {
|
| 11 |
+
"_name_or_path": "microsoft/BiomedVLP-CXR-BERT-general",
|
| 12 |
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"BertForMaskedLM"
|
| 15 |
+
],
|
| 16 |
"attention_probs_dropout_prob": 0.1,
|
| 17 |
"bad_words_ids": null,
|
| 18 |
"begin_suppress_tokens": null,
|
|
|
|
| 86 |
"typical_p": 1.0,
|
| 87 |
"use_bfloat16": false,
|
| 88 |
"use_cache": true,
|
| 89 |
+
"vocab_size": 30522
|
| 90 |
},
|
| 91 |
"torch_dtype": "float32",
|
| 92 |
"transformers_version": null,
|
| 93 |
"vision_config": {
|
| 94 |
+
"_name_or_path": "openai/clip-vit-large-patch14",
|
| 95 |
"add_cross_attention": false,
|
| 96 |
"architectures": null,
|
| 97 |
"attention_dropout": 0.0,
|
|
|
|
| 112 |
"forced_bos_token_id": null,
|
| 113 |
"forced_eos_token_id": null,
|
| 114 |
"hidden_act": "quick_gelu",
|
| 115 |
+
"hidden_size": 1024,
|
| 116 |
"id2label": {
|
| 117 |
"0": "LABEL_0",
|
| 118 |
"1": "LABEL_1"
|
|
|
|
| 120 |
"image_size": 224,
|
| 121 |
"initializer_factor": 1.0,
|
| 122 |
"initializer_range": 0.02,
|
| 123 |
+
"intermediate_size": 4096,
|
| 124 |
"is_decoder": false,
|
| 125 |
"is_encoder_decoder": false,
|
| 126 |
"label2id": {
|
|
|
|
| 133 |
"min_length": 0,
|
| 134 |
"model_type": "clip_vision_model",
|
| 135 |
"no_repeat_ngram_size": 0,
|
| 136 |
+
"num_attention_heads": 16,
|
| 137 |
"num_beam_groups": 1,
|
| 138 |
"num_beams": 1,
|
| 139 |
"num_channels": 3,
|
| 140 |
+
"num_hidden_layers": 24,
|
| 141 |
"num_return_sequences": 1,
|
| 142 |
"output_attentions": false,
|
| 143 |
"output_hidden_states": false,
|
| 144 |
"output_scores": false,
|
| 145 |
"pad_token_id": null,
|
| 146 |
+
"patch_size": 14,
|
| 147 |
"prefix": null,
|
| 148 |
"problem_type": null,
|
| 149 |
+
"projection_dim": 768,
|
| 150 |
"pruned_heads": {},
|
| 151 |
"remove_invalid_values": false,
|
| 152 |
"repetition_penalty": 1.0,
|
eval_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"eval_loss": 0.3388192057609558,
|
| 4 |
+
"eval_runtime": 139.1474,
|
| 5 |
+
"eval_samples_per_second": 58.743,
|
| 6 |
+
"eval_steps_per_second": 2.451
|
| 7 |
}
|
heatmap.png
ADDED
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:445915de1c92c4ae37a45cc24c1bf8ab0ed6f8be400e1c11c1a6c547c3327710
|
| 3 |
+
size 1654528401
|
runs/Jul07_03-20-36_pop-os/events.out.tfevents.1688696444.pop-os.586616.0
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:90dbb79765d47658ca4c94cd3d2c278ac6b3909023eb28140e1774790d45fac5
|
| 3 |
-
size 9270
|
|
|
|
|
|
|
|
|
|
|
|
runs/{Jul07_00-39-43_pop-os/events.out.tfevents.1688686792.pop-os.142684.0 → Jul08_01-50-48_pop-os/events.out.tfevents.1688777456.pop-os.224570.0}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc0246bec59f3c94b8c51e5a40440d678f8bd0af0d5e981478d4bed7234b3bd7
|
| 3 |
+
size 54222
|
runs/{Jul07_00-39-43_pop-os/events.out.tfevents.1688690222.pop-os.142684.1 → Jul08_01-50-48_pop-os/events.out.tfevents.1688822179.pop-os.224570.1}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97e679368a0c9b568c036dbf45af5c02f847eb4330a3943b1ef4cea2827cbd43
|
| 3 |
+
size 364
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"train_loss": 0.21080181559736064,
|
| 4 |
+
"train_runtime": 44575.4239,
|
| 5 |
+
"train_samples_per_second": 11.741,
|
| 6 |
+
"train_steps_per_second": 0.978
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,109 +1,1243 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss":
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"eval_loss": 1.
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
"step": 500
|
| 23 |
},
|
| 24 |
{
|
| 25 |
-
"epoch":
|
| 26 |
-
"learning_rate": 4.
|
| 27 |
-
"loss":
|
| 28 |
"step": 1000
|
| 29 |
},
|
| 30 |
{
|
| 31 |
-
"epoch":
|
| 32 |
-
"eval_loss": 0.
|
| 33 |
-
"eval_runtime":
|
| 34 |
-
"eval_samples_per_second":
|
| 35 |
-
"eval_steps_per_second":
|
| 36 |
"step": 1000
|
| 37 |
},
|
| 38 |
{
|
| 39 |
-
"epoch":
|
| 40 |
-
"learning_rate":
|
| 41 |
-
"loss": 0.
|
| 42 |
"step": 1500
|
| 43 |
},
|
| 44 |
{
|
| 45 |
-
"epoch":
|
| 46 |
-
"eval_loss": 0.
|
| 47 |
-
"eval_runtime":
|
| 48 |
-
"eval_samples_per_second":
|
| 49 |
-
"eval_steps_per_second":
|
| 50 |
"step": 1500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 2000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"eval_loss": 0.
|
| 61 |
-
"eval_runtime":
|
| 62 |
-
"eval_samples_per_second":
|
| 63 |
-
"eval_steps_per_second":
|
| 64 |
"step": 2000
|
| 65 |
},
|
| 66 |
{
|
| 67 |
-
"epoch":
|
| 68 |
-
"learning_rate":
|
| 69 |
-
"loss": 0.
|
| 70 |
"step": 2500
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"epoch":
|
| 74 |
-
"eval_loss": 0.
|
| 75 |
-
"eval_runtime":
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second":
|
| 78 |
"step": 2500
|
| 79 |
},
|
| 80 |
{
|
| 81 |
-
"epoch":
|
| 82 |
-
"learning_rate":
|
| 83 |
-
"loss": 0.
|
| 84 |
"step": 3000
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"epoch":
|
| 88 |
-
"eval_loss": 0.
|
| 89 |
-
"eval_runtime":
|
| 90 |
-
"eval_samples_per_second":
|
| 91 |
-
"eval_steps_per_second":
|
| 92 |
"step": 3000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
}
|
| 103 |
],
|
| 104 |
-
"max_steps":
|
| 105 |
-
"num_train_epochs":
|
| 106 |
-
"total_flos":
|
| 107 |
"trial_name": null,
|
| 108 |
"trial_params": null
|
| 109 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.3388192057609558,
|
| 3 |
+
"best_model_checkpoint": "outputs/output_8_clip14_cxrbert/checkpoint-22500",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 43608,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 4.999999755266707e-05,
|
| 13 |
+
"loss": 0.7951,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"eval_loss": 1.1912389993667603,
|
| 19 |
+
"eval_runtime": 139.1386,
|
| 20 |
+
"eval_samples_per_second": 58.747,
|
| 21 |
+
"eval_steps_per_second": 2.451,
|
| 22 |
"step": 500
|
| 23 |
},
|
| 24 |
{
|
| 25 |
+
"epoch": 0.18,
|
| 26 |
+
"learning_rate": 4.993123185382302e-05,
|
| 27 |
+
"loss": 0.5887,
|
| 28 |
"step": 1000
|
| 29 |
},
|
| 30 |
{
|
| 31 |
+
"epoch": 0.18,
|
| 32 |
+
"eval_loss": 0.9833270907402039,
|
| 33 |
+
"eval_runtime": 139.0379,
|
| 34 |
+
"eval_samples_per_second": 58.79,
|
| 35 |
+
"eval_steps_per_second": 2.453,
|
| 36 |
"step": 1000
|
| 37 |
},
|
| 38 |
{
|
| 39 |
+
"epoch": 0.28,
|
| 40 |
+
"learning_rate": 4.972693864808811e-05,
|
| 41 |
+
"loss": 0.5023,
|
| 42 |
"step": 1500
|
| 43 |
},
|
| 44 |
{
|
| 45 |
+
"epoch": 0.28,
|
| 46 |
+
"eval_loss": 0.8458877205848694,
|
| 47 |
+
"eval_runtime": 139.1851,
|
| 48 |
+
"eval_samples_per_second": 58.728,
|
| 49 |
+
"eval_steps_per_second": 2.45,
|
| 50 |
"step": 1500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.37,
|
| 54 |
+
"learning_rate": 4.938822848423147e-05,
|
| 55 |
+
"loss": 0.4709,
|
| 56 |
"step": 2000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.37,
|
| 60 |
+
"eval_loss": 0.8479061126708984,
|
| 61 |
+
"eval_runtime": 138.6519,
|
| 62 |
+
"eval_samples_per_second": 58.953,
|
| 63 |
+
"eval_steps_per_second": 2.459,
|
| 64 |
"step": 2000
|
| 65 |
},
|
| 66 |
{
|
| 67 |
+
"epoch": 0.46,
|
| 68 |
+
"learning_rate": 4.891694260878015e-05,
|
| 69 |
+
"loss": 0.4484,
|
| 70 |
"step": 2500
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"epoch": 0.46,
|
| 74 |
+
"eval_loss": 0.766708493232727,
|
| 75 |
+
"eval_runtime": 138.9466,
|
| 76 |
+
"eval_samples_per_second": 58.828,
|
| 77 |
+
"eval_steps_per_second": 2.454,
|
| 78 |
"step": 2500
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 0.55,
|
| 82 |
+
"learning_rate": 4.831564295690475e-05,
|
| 83 |
+
"loss": 0.4319,
|
| 84 |
"step": 3000
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 0.55,
|
| 88 |
+
"eval_loss": 0.8092461228370667,
|
| 89 |
+
"eval_runtime": 138.9741,
|
| 90 |
+
"eval_samples_per_second": 58.817,
|
| 91 |
+
"eval_steps_per_second": 2.454,
|
| 92 |
"step": 3000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.64,
|
| 96 |
+
"learning_rate": 4.7587598225603125e-05,
|
| 97 |
+
"loss": 0.4181,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.64,
|
| 102 |
+
"eval_loss": 0.6963649392127991,
|
| 103 |
+
"eval_runtime": 138.9254,
|
| 104 |
+
"eval_samples_per_second": 58.837,
|
| 105 |
+
"eval_steps_per_second": 2.455,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.73,
|
| 110 |
+
"learning_rate": 4.673676610488902e-05,
|
| 111 |
+
"loss": 0.4107,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.73,
|
| 116 |
+
"eval_loss": 0.6463401913642883,
|
| 117 |
+
"eval_runtime": 138.8758,
|
| 118 |
+
"eval_samples_per_second": 58.858,
|
| 119 |
+
"eval_steps_per_second": 2.455,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.83,
|
| 124 |
+
"learning_rate": 4.576777176357795e-05,
|
| 125 |
+
"loss": 0.3723,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.83,
|
| 130 |
+
"eval_loss": 0.7892907857894897,
|
| 131 |
+
"eval_runtime": 138.7167,
|
| 132 |
+
"eval_samples_per_second": 58.926,
|
| 133 |
+
"eval_steps_per_second": 2.458,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.92,
|
| 138 |
+
"learning_rate": 4.468588270662272e-05,
|
| 139 |
+
"loss": 0.3746,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.92,
|
| 144 |
+
"eval_loss": 0.686305582523346,
|
| 145 |
+
"eval_runtime": 139.0126,
|
| 146 |
+
"eval_samples_per_second": 58.8,
|
| 147 |
+
"eval_steps_per_second": 2.453,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.01,
|
| 152 |
+
"learning_rate": 4.349698014067534e-05,
|
| 153 |
+
"loss": 0.3667,
|
| 154 |
+
"step": 5500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.01,
|
| 158 |
+
"eval_loss": 0.6910073161125183,
|
| 159 |
+
"eval_runtime": 138.8546,
|
| 160 |
+
"eval_samples_per_second": 58.867,
|
| 161 |
+
"eval_steps_per_second": 2.456,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.1,
|
| 166 |
+
"learning_rate": 4.220752700353382e-05,
|
| 167 |
+
"loss": 0.3253,
|
| 168 |
+
"step": 6000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.1,
|
| 172 |
+
"eval_loss": 0.6863256096839905,
|
| 173 |
+
"eval_runtime": 138.8547,
|
| 174 |
+
"eval_samples_per_second": 58.867,
|
| 175 |
+
"eval_steps_per_second": 2.456,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.19,
|
| 180 |
+
"learning_rate": 4.082453283126738e-05,
|
| 181 |
+
"loss": 0.3274,
|
| 182 |
+
"step": 6500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.19,
|
| 186 |
+
"eval_loss": 0.6445034146308899,
|
| 187 |
+
"eval_runtime": 138.846,
|
| 188 |
+
"eval_samples_per_second": 58.871,
|
| 189 |
+
"eval_steps_per_second": 2.456,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.28,
|
| 194 |
+
"learning_rate": 3.935551565400428e-05,
|
| 195 |
+
"loss": 0.3065,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.28,
|
| 200 |
+
"eval_loss": 0.5908203125,
|
| 201 |
+
"eval_runtime": 138.7486,
|
| 202 |
+
"eval_samples_per_second": 58.912,
|
| 203 |
+
"eval_steps_per_second": 2.458,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.38,
|
| 208 |
+
"learning_rate": 3.7808461127518854e-05,
|
| 209 |
+
"loss": 0.2834,
|
| 210 |
+
"step": 7500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.38,
|
| 214 |
+
"eval_loss": 0.6137728691101074,
|
| 215 |
+
"eval_runtime": 139.0095,
|
| 216 |
+
"eval_samples_per_second": 58.802,
|
| 217 |
+
"eval_steps_per_second": 2.453,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.47,
|
| 222 |
+
"learning_rate": 3.6191779122780486e-05,
|
| 223 |
+
"loss": 0.293,
|
| 224 |
+
"step": 8000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.47,
|
| 228 |
+
"eval_loss": 0.6515378355979919,
|
| 229 |
+
"eval_runtime": 139.1162,
|
| 230 |
+
"eval_samples_per_second": 58.757,
|
| 231 |
+
"eval_steps_per_second": 2.451,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.56,
|
| 236 |
+
"learning_rate": 3.4514258009446234e-05,
|
| 237 |
+
"loss": 0.303,
|
| 238 |
+
"step": 8500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.56,
|
| 242 |
+
"eval_loss": 0.5806155800819397,
|
| 243 |
+
"eval_runtime": 138.924,
|
| 244 |
+
"eval_samples_per_second": 58.838,
|
| 245 |
+
"eval_steps_per_second": 2.455,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.65,
|
| 250 |
+
"learning_rate": 3.278501688181439e-05,
|
| 251 |
+
"loss": 0.2638,
|
| 252 |
+
"step": 9000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.65,
|
| 256 |
+
"eval_loss": 0.5586961507797241,
|
| 257 |
+
"eval_runtime": 139.1301,
|
| 258 |
+
"eval_samples_per_second": 58.751,
|
| 259 |
+
"eval_steps_per_second": 2.451,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.74,
|
| 264 |
+
"learning_rate": 3.101345598694112e-05,
|
| 265 |
+
"loss": 0.2593,
|
| 266 |
+
"step": 9500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.74,
|
| 270 |
+
"eval_loss": 0.5215563178062439,
|
| 271 |
+
"eval_runtime": 138.9957,
|
| 272 |
+
"eval_samples_per_second": 58.808,
|
| 273 |
+
"eval_steps_per_second": 2.453,
|
| 274 |
+
"step": 9500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.83,
|
| 278 |
+
"learning_rate": 2.9209205624395885e-05,
|
| 279 |
+
"loss": 0.2451,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.83,
|
| 284 |
+
"eval_loss": 0.5282728672027588,
|
| 285 |
+
"eval_runtime": 138.8608,
|
| 286 |
+
"eval_samples_per_second": 58.865,
|
| 287 |
+
"eval_steps_per_second": 2.456,
|
| 288 |
+
"step": 10000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.93,
|
| 292 |
+
"learning_rate": 2.7382073795438957e-05,
|
| 293 |
+
"loss": 0.2468,
|
| 294 |
+
"step": 10500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.93,
|
| 298 |
+
"eval_loss": 0.5001487135887146,
|
| 299 |
+
"eval_runtime": 138.9207,
|
| 300 |
+
"eval_samples_per_second": 58.839,
|
| 301 |
+
"eval_steps_per_second": 2.455,
|
| 302 |
+
"step": 10500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.02,
|
| 306 |
+
"learning_rate": 2.5541992886203175e-05,
|
| 307 |
+
"loss": 0.2295,
|
| 308 |
+
"step": 11000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.02,
|
| 312 |
+
"eval_loss": 0.49750879406929016,
|
| 313 |
+
"eval_runtime": 138.9502,
|
| 314 |
+
"eval_samples_per_second": 58.827,
|
| 315 |
+
"eval_steps_per_second": 2.454,
|
| 316 |
+
"step": 11000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.11,
|
| 320 |
+
"learning_rate": 2.3698965674712838e-05,
|
| 321 |
+
"loss": 0.1953,
|
| 322 |
+
"step": 11500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.11,
|
| 326 |
+
"eval_loss": 0.4750489890575409,
|
| 327 |
+
"eval_runtime": 138.8668,
|
| 328 |
+
"eval_samples_per_second": 58.862,
|
| 329 |
+
"eval_steps_per_second": 2.456,
|
| 330 |
+
"step": 11500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.2,
|
| 334 |
+
"learning_rate": 2.1863010955248543e-05,
|
| 335 |
+
"loss": 0.1954,
|
| 336 |
+
"step": 12000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.2,
|
| 340 |
+
"eval_loss": 0.45723679661750793,
|
| 341 |
+
"eval_runtime": 139.0817,
|
| 342 |
+
"eval_samples_per_second": 58.771,
|
| 343 |
+
"eval_steps_per_second": 2.452,
|
| 344 |
+
"step": 12000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.29,
|
| 348 |
+
"learning_rate": 2.0044109075646793e-05,
|
| 349 |
+
"loss": 0.1737,
|
| 350 |
+
"step": 12500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.29,
|
| 354 |
+
"eval_loss": 0.4731180667877197,
|
| 355 |
+
"eval_runtime": 139.0822,
|
| 356 |
+
"eval_samples_per_second": 58.771,
|
| 357 |
+
"eval_steps_per_second": 2.452,
|
| 358 |
+
"step": 12500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.38,
|
| 362 |
+
"learning_rate": 1.8252147683596503e-05,
|
| 363 |
+
"loss": 0.175,
|
| 364 |
+
"step": 13000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.38,
|
| 368 |
+
"eval_loss": 0.4526049494743347,
|
| 369 |
+
"eval_runtime": 139.059,
|
| 370 |
+
"eval_samples_per_second": 58.781,
|
| 371 |
+
"eval_steps_per_second": 2.452,
|
| 372 |
+
"step": 13000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.48,
|
| 376 |
+
"learning_rate": 1.6496867976858525e-05,
|
| 377 |
+
"loss": 0.1873,
|
| 378 |
+
"step": 13500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.48,
|
| 382 |
+
"eval_loss": 0.4890150725841522,
|
| 383 |
+
"eval_runtime": 138.99,
|
| 384 |
+
"eval_samples_per_second": 58.81,
|
| 385 |
+
"eval_steps_per_second": 2.453,
|
| 386 |
+
"step": 13500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.57,
|
| 390 |
+
"learning_rate": 1.4787811749594674e-05,
|
| 391 |
+
"loss": 0.1809,
|
| 392 |
+
"step": 14000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.57,
|
| 396 |
+
"eval_loss": 0.4210197627544403,
|
| 397 |
+
"eval_runtime": 139.0599,
|
| 398 |
+
"eval_samples_per_second": 58.78,
|
| 399 |
+
"eval_steps_per_second": 2.452,
|
| 400 |
+
"step": 14000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.66,
|
| 404 |
+
"learning_rate": 1.3134269522665521e-05,
|
| 405 |
+
"loss": 0.1711,
|
| 406 |
+
"step": 14500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.66,
|
| 410 |
+
"eval_loss": 0.4197298586368561,
|
| 411 |
+
"eval_runtime": 139.0776,
|
| 412 |
+
"eval_samples_per_second": 58.773,
|
| 413 |
+
"eval_steps_per_second": 2.452,
|
| 414 |
+
"step": 14500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.75,
|
| 418 |
+
"learning_rate": 1.1545230039863117e-05,
|
| 419 |
+
"loss": 0.1457,
|
| 420 |
+
"step": 15000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.75,
|
| 424 |
+
"eval_loss": 0.3998343348503113,
|
| 425 |
+
"eval_runtime": 138.7787,
|
| 426 |
+
"eval_samples_per_second": 58.9,
|
| 427 |
+
"eval_steps_per_second": 2.457,
|
| 428 |
+
"step": 15000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.84,
|
| 432 |
+
"learning_rate": 1.0029331404620077e-05,
|
| 433 |
+
"loss": 0.1583,
|
| 434 |
+
"step": 15500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.84,
|
| 438 |
+
"eval_loss": 0.392282098531723,
|
| 439 |
+
"eval_runtime": 139.0688,
|
| 440 |
+
"eval_samples_per_second": 58.777,
|
| 441 |
+
"eval_steps_per_second": 2.452,
|
| 442 |
+
"step": 15500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.94,
|
| 446 |
+
"learning_rate": 8.59481412281825e-06,
|
| 447 |
+
"loss": 0.1579,
|
| 448 |
+
"step": 16000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.94,
|
| 452 |
+
"eval_loss": 0.3823428750038147,
|
| 453 |
+
"eval_runtime": 139.0069,
|
| 454 |
+
"eval_samples_per_second": 58.803,
|
| 455 |
+
"eval_steps_per_second": 2.453,
|
| 456 |
+
"step": 16000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.03,
|
| 460 |
+
"learning_rate": 7.249476306959052e-06,
|
| 461 |
+
"loss": 0.1339,
|
| 462 |
+
"step": 16500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 3.03,
|
| 466 |
+
"eval_loss": 0.3654000163078308,
|
| 467 |
+
"eval_runtime": 139.085,
|
| 468 |
+
"eval_samples_per_second": 58.77,
|
| 469 |
+
"eval_steps_per_second": 2.452,
|
| 470 |
+
"step": 16500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.12,
|
| 474 |
+
"learning_rate": 6.00063128520765e-06,
|
| 475 |
+
"loss": 0.1164,
|
| 476 |
+
"step": 17000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.12,
|
| 480 |
+
"eval_loss": 0.3591544032096863,
|
| 481 |
+
"eval_runtime": 139.2185,
|
| 482 |
+
"eval_samples_per_second": 58.713,
|
| 483 |
+
"eval_steps_per_second": 2.449,
|
| 484 |
+
"step": 17000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.21,
|
| 488 |
+
"learning_rate": 4.855067845750841e-06,
|
| 489 |
+
"loss": 0.1217,
|
| 490 |
+
"step": 17500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.21,
|
| 494 |
+
"eval_loss": 0.3641490936279297,
|
| 495 |
+
"eval_runtime": 139.1903,
|
| 496 |
+
"eval_samples_per_second": 58.725,
|
| 497 |
+
"eval_steps_per_second": 2.45,
|
| 498 |
+
"step": 17500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.3,
|
| 502 |
+
"learning_rate": 3.8190133325820834e-06,
|
| 503 |
+
"loss": 0.119,
|
| 504 |
+
"step": 18000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.3,
|
| 508 |
+
"eval_loss": 0.3553272783756256,
|
| 509 |
+
"eval_runtime": 139.0893,
|
| 510 |
+
"eval_samples_per_second": 58.768,
|
| 511 |
+
"eval_steps_per_second": 2.452,
|
| 512 |
+
"step": 18000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.39,
|
| 516 |
+
"learning_rate": 2.8980997933272802e-06,
|
| 517 |
+
"loss": 0.1151,
|
| 518 |
+
"step": 18500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.39,
|
| 522 |
+
"eval_loss": 0.35238373279571533,
|
| 523 |
+
"eval_runtime": 139.0702,
|
| 524 |
+
"eval_samples_per_second": 58.776,
|
| 525 |
+
"eval_steps_per_second": 2.452,
|
| 526 |
+
"step": 18500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.49,
|
| 530 |
+
"learning_rate": 2.0973333631332525e-06,
|
| 531 |
+
"loss": 0.119,
|
| 532 |
+
"step": 19000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.49,
|
| 536 |
+
"eval_loss": 0.3452140688896179,
|
| 537 |
+
"eval_runtime": 138.934,
|
| 538 |
+
"eval_samples_per_second": 58.834,
|
| 539 |
+
"eval_steps_per_second": 2.454,
|
| 540 |
+
"step": 19000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.58,
|
| 544 |
+
"learning_rate": 1.4210670510499595e-06,
|
| 545 |
+
"loss": 0.102,
|
| 546 |
+
"step": 19500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.58,
|
| 550 |
+
"eval_loss": 0.34390997886657715,
|
| 551 |
+
"eval_runtime": 139.1805,
|
| 552 |
+
"eval_samples_per_second": 58.729,
|
| 553 |
+
"eval_steps_per_second": 2.45,
|
| 554 |
+
"step": 19500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.67,
|
| 558 |
+
"learning_rate": 8.729770768409501e-07,
|
| 559 |
+
"loss": 0.1085,
|
| 560 |
+
"step": 20000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.67,
|
| 564 |
+
"eval_loss": 0.3422289192676544,
|
| 565 |
+
"eval_runtime": 139.0942,
|
| 566 |
+
"eval_samples_per_second": 58.766,
|
| 567 |
+
"eval_steps_per_second": 2.452,
|
| 568 |
+
"step": 20000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.76,
|
| 572 |
+
"learning_rate": 4.5604288685657804e-07,
|
| 573 |
+
"loss": 0.1142,
|
| 574 |
+
"step": 20500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 3.76,
|
| 578 |
+
"eval_loss": 0.33955371379852295,
|
| 579 |
+
"eval_runtime": 138.9826,
|
| 580 |
+
"eval_samples_per_second": 58.813,
|
| 581 |
+
"eval_steps_per_second": 2.454,
|
| 582 |
+
"step": 20500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.85,
|
| 586 |
+
"learning_rate": 1.7253095760459415e-07,
|
| 587 |
+
"loss": 0.1038,
|
| 588 |
+
"step": 21000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 3.85,
|
| 592 |
+
"eval_loss": 0.33917009830474854,
|
| 593 |
+
"eval_runtime": 139.1121,
|
| 594 |
+
"eval_samples_per_second": 58.758,
|
| 595 |
+
"eval_steps_per_second": 2.451,
|
| 596 |
+
"step": 21000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.94,
|
| 600 |
+
"learning_rate": 2.3982475062916954e-08,
|
| 601 |
+
"loss": 0.1143,
|
| 602 |
+
"step": 21500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.94,
|
| 606 |
+
"eval_loss": 0.33897778391838074,
|
| 607 |
+
"eval_runtime": 139.1906,
|
| 608 |
+
"eval_samples_per_second": 58.725,
|
| 609 |
+
"eval_steps_per_second": 2.45,
|
| 610 |
+
"step": 21500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 4.04,
|
| 614 |
+
"learning_rate": 1.1204956710403336e-08,
|
| 615 |
+
"loss": 0.0983,
|
| 616 |
+
"step": 22000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 4.04,
|
| 620 |
+
"eval_loss": 0.3389684855937958,
|
| 621 |
+
"eval_runtime": 139.2217,
|
| 622 |
+
"eval_samples_per_second": 58.712,
|
| 623 |
+
"eval_steps_per_second": 2.449,
|
| 624 |
+
"step": 22000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.13,
|
| 628 |
+
"learning_rate": 1.3426786181872375e-07,
|
| 629 |
+
"loss": 0.0974,
|
| 630 |
+
"step": 22500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 4.13,
|
| 634 |
+
"eval_loss": 0.3388192057609558,
|
| 635 |
+
"eval_runtime": 139.1103,
|
| 636 |
+
"eval_samples_per_second": 58.759,
|
| 637 |
+
"eval_steps_per_second": 2.451,
|
| 638 |
+
"step": 22500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.22,
|
| 642 |
+
"learning_rate": 3.925022138680762e-07,
|
| 643 |
+
"loss": 0.1007,
|
| 644 |
+
"step": 23000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 4.22,
|
| 648 |
+
"eval_loss": 0.33886849880218506,
|
| 649 |
+
"eval_runtime": 139.2186,
|
| 650 |
+
"eval_samples_per_second": 58.713,
|
| 651 |
+
"eval_steps_per_second": 2.449,
|
| 652 |
+
"step": 23000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 4.31,
|
| 656 |
+
"learning_rate": 7.845042371392303e-07,
|
| 657 |
+
"loss": 0.0903,
|
| 658 |
+
"step": 23500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 4.31,
|
| 662 |
+
"eval_loss": 0.33964774012565613,
|
| 663 |
+
"eval_runtime": 139.1917,
|
| 664 |
+
"eval_samples_per_second": 58.725,
|
| 665 |
+
"eval_steps_per_second": 2.45,
|
| 666 |
+
"step": 23500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 4.4,
|
| 670 |
+
"learning_rate": 1.308142987713265e-06,
|
| 671 |
+
"loss": 0.095,
|
| 672 |
+
"step": 24000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 4.4,
|
| 676 |
+
"eval_loss": 0.3394069969654083,
|
| 677 |
+
"eval_runtime": 139.0407,
|
| 678 |
+
"eval_samples_per_second": 58.789,
|
| 679 |
+
"eval_steps_per_second": 2.453,
|
| 680 |
+
"step": 24000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.49,
|
| 684 |
+
"learning_rate": 1.960571937396438e-06,
|
| 685 |
+
"loss": 0.0955,
|
| 686 |
+
"step": 24500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 4.49,
|
| 690 |
+
"eval_loss": 0.3435823619365692,
|
| 691 |
+
"eval_runtime": 138.8656,
|
| 692 |
+
"eval_samples_per_second": 58.863,
|
| 693 |
+
"eval_steps_per_second": 2.456,
|
| 694 |
+
"step": 24500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.59,
|
| 698 |
+
"learning_rate": 2.7382444475993473e-06,
|
| 699 |
+
"loss": 0.1032,
|
| 700 |
+
"step": 25000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 4.59,
|
| 704 |
+
"eval_loss": 0.3425971269607544,
|
| 705 |
+
"eval_runtime": 139.1498,
|
| 706 |
+
"eval_samples_per_second": 58.742,
|
| 707 |
+
"eval_steps_per_second": 2.451,
|
| 708 |
+
"step": 25000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 4.68,
|
| 712 |
+
"learning_rate": 3.636933049053598e-06,
|
| 713 |
+
"loss": 0.1037,
|
| 714 |
+
"step": 25500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.68,
|
| 718 |
+
"eval_loss": 0.3484514653682709,
|
| 719 |
+
"eval_runtime": 139.2414,
|
| 720 |
+
"eval_samples_per_second": 58.704,
|
| 721 |
+
"eval_steps_per_second": 2.449,
|
| 722 |
+
"step": 25500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 4.77,
|
| 726 |
+
"learning_rate": 4.651752422560337e-06,
|
| 727 |
+
"loss": 0.103,
|
| 728 |
+
"step": 26000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 4.77,
|
| 732 |
+
"eval_loss": 0.35472801327705383,
|
| 733 |
+
"eval_runtime": 139.171,
|
| 734 |
+
"eval_samples_per_second": 58.733,
|
| 735 |
+
"eval_steps_per_second": 2.45,
|
| 736 |
+
"step": 26000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 4.86,
|
| 740 |
+
"learning_rate": 5.777185955846176e-06,
|
| 741 |
+
"loss": 0.0987,
|
| 742 |
+
"step": 26500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 4.86,
|
| 746 |
+
"eval_loss": 0.355197936296463,
|
| 747 |
+
"eval_runtime": 139.255,
|
| 748 |
+
"eval_samples_per_second": 58.698,
|
| 749 |
+
"eval_steps_per_second": 2.449,
|
| 750 |
+
"step": 26500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 4.95,
|
| 754 |
+
"learning_rate": 7.007115732161859e-06,
|
| 755 |
+
"loss": 0.1076,
|
| 756 |
+
"step": 27000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 4.95,
|
| 760 |
+
"eval_loss": 0.35372602939605713,
|
| 761 |
+
"eval_runtime": 139.256,
|
| 762 |
+
"eval_samples_per_second": 58.698,
|
| 763 |
+
"eval_steps_per_second": 2.449,
|
| 764 |
+
"step": 27000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 5.04,
|
| 768 |
+
"learning_rate": 8.334855787604286e-06,
|
| 769 |
+
"loss": 0.1134,
|
| 770 |
+
"step": 27500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 5.04,
|
| 774 |
+
"eval_loss": 0.35491758584976196,
|
| 775 |
+
"eval_runtime": 139.157,
|
| 776 |
+
"eval_samples_per_second": 58.739,
|
| 777 |
+
"eval_steps_per_second": 2.45,
|
| 778 |
+
"step": 27500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 5.14,
|
| 782 |
+
"learning_rate": 9.753188456373041e-06,
|
| 783 |
+
"loss": 0.1044,
|
| 784 |
+
"step": 28000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 5.14,
|
| 788 |
+
"eval_loss": 0.362209677696228,
|
| 789 |
+
"eval_runtime": 139.1058,
|
| 790 |
+
"eval_samples_per_second": 58.761,
|
| 791 |
+
"eval_steps_per_second": 2.451,
|
| 792 |
+
"step": 28000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 5.23,
|
| 796 |
+
"learning_rate": 1.1254403606386926e-05,
|
| 797 |
+
"loss": 0.1099,
|
| 798 |
+
"step": 28500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 5.23,
|
| 802 |
+
"eval_loss": 0.37740227580070496,
|
| 803 |
+
"eval_runtime": 139.2551,
|
| 804 |
+
"eval_samples_per_second": 58.698,
|
| 805 |
+
"eval_steps_per_second": 2.449,
|
| 806 |
+
"step": 28500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 5.32,
|
| 810 |
+
"learning_rate": 1.2830340551973424e-05,
|
| 811 |
+
"loss": 0.1129,
|
| 812 |
+
"step": 29000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 5.32,
|
| 816 |
+
"eval_loss": 0.387184202671051,
|
| 817 |
+
"eval_runtime": 138.9995,
|
| 818 |
+
"eval_samples_per_second": 58.806,
|
| 819 |
+
"eval_steps_per_second": 2.453,
|
| 820 |
+
"step": 29000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 5.41,
|
| 824 |
+
"learning_rate": 1.4472432415791445e-05,
|
| 825 |
+
"loss": 0.1235,
|
| 826 |
+
"step": 29500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 5.41,
|
| 830 |
+
"eval_loss": 0.3766579329967499,
|
| 831 |
+
"eval_runtime": 139.1988,
|
| 832 |
+
"eval_samples_per_second": 58.722,
|
| 833 |
+
"eval_steps_per_second": 2.45,
|
| 834 |
+
"step": 29500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 5.5,
|
| 838 |
+
"learning_rate": 1.6171752698833968e-05,
|
| 839 |
+
"loss": 0.1099,
|
| 840 |
+
"step": 30000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 5.5,
|
| 844 |
+
"eval_loss": 0.3879966139793396,
|
| 845 |
+
"eval_runtime": 139.1987,
|
| 846 |
+
"eval_samples_per_second": 58.722,
|
| 847 |
+
"eval_steps_per_second": 2.45,
|
| 848 |
+
"step": 30000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 5.6,
|
| 852 |
+
"learning_rate": 1.7919063805352744e-05,
|
| 853 |
+
"loss": 0.1331,
|
| 854 |
+
"step": 30500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 5.6,
|
| 858 |
+
"eval_loss": 0.41808027029037476,
|
| 859 |
+
"eval_runtime": 139.3796,
|
| 860 |
+
"eval_samples_per_second": 58.646,
|
| 861 |
+
"eval_steps_per_second": 2.447,
|
| 862 |
+
"step": 30500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 5.69,
|
| 866 |
+
"learning_rate": 1.9704867258922042e-05,
|
| 867 |
+
"loss": 0.134,
|
| 868 |
+
"step": 31000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 5.69,
|
| 872 |
+
"eval_loss": 0.4090297818183899,
|
| 873 |
+
"eval_runtime": 139.2797,
|
| 874 |
+
"eval_samples_per_second": 58.688,
|
| 875 |
+
"eval_steps_per_second": 2.448,
|
| 876 |
+
"step": 31000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 5.78,
|
| 880 |
+
"learning_rate": 2.1519455336663182e-05,
|
| 881 |
+
"loss": 0.142,
|
| 882 |
+
"step": 31500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 5.78,
|
| 886 |
+
"eval_loss": 0.4044671654701233,
|
| 887 |
+
"eval_runtime": 139.2242,
|
| 888 |
+
"eval_samples_per_second": 58.711,
|
| 889 |
+
"eval_steps_per_second": 2.449,
|
| 890 |
+
"step": 31500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 5.87,
|
| 894 |
+
"learning_rate": 2.335296384094446e-05,
|
| 895 |
+
"loss": 0.1441,
|
| 896 |
+
"step": 32000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 5.87,
|
| 900 |
+
"eval_loss": 0.41757142543792725,
|
| 901 |
+
"eval_runtime": 139.1671,
|
| 902 |
+
"eval_samples_per_second": 58.735,
|
| 903 |
+
"eval_steps_per_second": 2.45,
|
| 904 |
+
"step": 32000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 5.96,
|
| 908 |
+
"learning_rate": 2.51954257216856e-05,
|
| 909 |
+
"loss": 0.1577,
|
| 910 |
+
"step": 32500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 5.96,
|
| 914 |
+
"eval_loss": 0.43774479627609253,
|
| 915 |
+
"eval_runtime": 139.219,
|
| 916 |
+
"eval_samples_per_second": 58.713,
|
| 917 |
+
"eval_steps_per_second": 2.449,
|
| 918 |
+
"step": 32500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 6.05,
|
| 922 |
+
"learning_rate": 2.703682525777417e-05,
|
| 923 |
+
"loss": 0.1539,
|
| 924 |
+
"step": 33000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 6.05,
|
| 928 |
+
"eval_loss": 0.43269890546798706,
|
| 929 |
+
"eval_runtime": 139.3068,
|
| 930 |
+
"eval_samples_per_second": 58.676,
|
| 931 |
+
"eval_steps_per_second": 2.448,
|
| 932 |
+
"step": 33000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 6.15,
|
| 936 |
+
"learning_rate": 2.8867152503059856e-05,
|
| 937 |
+
"loss": 0.1475,
|
| 938 |
+
"step": 33500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 6.15,
|
| 942 |
+
"eval_loss": 0.4586590826511383,
|
| 943 |
+
"eval_runtime": 139.2759,
|
| 944 |
+
"eval_samples_per_second": 58.689,
|
| 945 |
+
"eval_steps_per_second": 2.448,
|
| 946 |
+
"step": 33500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 6.24,
|
| 950 |
+
"learning_rate": 3.0676457700956226e-05,
|
| 951 |
+
"loss": 0.1616,
|
| 952 |
+
"step": 34000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 6.24,
|
| 956 |
+
"eval_loss": 0.47090479731559753,
|
| 957 |
+
"eval_runtime": 139.1928,
|
| 958 |
+
"eval_samples_per_second": 58.724,
|
| 959 |
+
"eval_steps_per_second": 2.45,
|
| 960 |
+
"step": 34000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 6.33,
|
| 964 |
+
"learning_rate": 3.2454905371848176e-05,
|
| 965 |
+
"loss": 0.1671,
|
| 966 |
+
"step": 34500
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 6.33,
|
| 970 |
+
"eval_loss": 0.49197548627853394,
|
| 971 |
+
"eval_runtime": 139.1637,
|
| 972 |
+
"eval_samples_per_second": 58.737,
|
| 973 |
+
"eval_steps_per_second": 2.45,
|
| 974 |
+
"step": 34500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 6.42,
|
| 978 |
+
"learning_rate": 3.4192827779284355e-05,
|
| 979 |
+
"loss": 0.1792,
|
| 980 |
+
"step": 35000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 6.42,
|
| 984 |
+
"eval_loss": 0.48025813698768616,
|
| 985 |
+
"eval_runtime": 139.2895,
|
| 986 |
+
"eval_samples_per_second": 58.684,
|
| 987 |
+
"eval_steps_per_second": 2.448,
|
| 988 |
+
"step": 35000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 6.51,
|
| 992 |
+
"learning_rate": 3.588077748430818e-05,
|
| 993 |
+
"loss": 0.2025,
|
| 994 |
+
"step": 35500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 6.51,
|
| 998 |
+
"eval_loss": 0.5274905562400818,
|
| 999 |
+
"eval_runtime": 138.8747,
|
| 1000 |
+
"eval_samples_per_second": 58.859,
|
| 1001 |
+
"eval_steps_per_second": 2.455,
|
| 1002 |
+
"step": 35500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 6.6,
|
| 1006 |
+
"learning_rate": 3.7509578702240475e-05,
|
| 1007 |
+
"loss": 0.1823,
|
| 1008 |
+
"step": 36000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 6.6,
|
| 1012 |
+
"eval_loss": 0.5114786028862,
|
| 1013 |
+
"eval_runtime": 139.2682,
|
| 1014 |
+
"eval_samples_per_second": 58.692,
|
| 1015 |
+
"eval_steps_per_second": 2.449,
|
| 1016 |
+
"step": 36000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 6.7,
|
| 1020 |
+
"learning_rate": 3.9070377182734444e-05,
|
| 1021 |
+
"loss": 0.2123,
|
| 1022 |
+
"step": 36500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 6.7,
|
| 1026 |
+
"eval_loss": 0.4975065290927887,
|
| 1027 |
+
"eval_runtime": 138.9217,
|
| 1028 |
+
"eval_samples_per_second": 58.839,
|
| 1029 |
+
"eval_steps_per_second": 2.455,
|
| 1030 |
+
"step": 36500
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 6.79,
|
| 1034 |
+
"learning_rate": 4.0554688341953205e-05,
|
| 1035 |
+
"loss": 0.2043,
|
| 1036 |
+
"step": 37000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 6.79,
|
| 1040 |
+
"eval_loss": 0.48896968364715576,
|
| 1041 |
+
"eval_runtime": 139.3258,
|
| 1042 |
+
"eval_samples_per_second": 58.668,
|
| 1043 |
+
"eval_steps_per_second": 2.448,
|
| 1044 |
+
"step": 37000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 6.88,
|
| 1048 |
+
"learning_rate": 4.19544433852203e-05,
|
| 1049 |
+
"loss": 0.2086,
|
| 1050 |
+
"step": 37500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 6.88,
|
| 1054 |
+
"eval_loss": 0.5374048352241516,
|
| 1055 |
+
"eval_runtime": 139.1786,
|
| 1056 |
+
"eval_samples_per_second": 58.73,
|
| 1057 |
+
"eval_steps_per_second": 2.45,
|
| 1058 |
+
"step": 37500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 6.97,
|
| 1062 |
+
"learning_rate": 4.326203316941825e-05,
|
| 1063 |
+
"loss": 0.2299,
|
| 1064 |
+
"step": 38000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 6.97,
|
| 1068 |
+
"eval_loss": 0.5565398335456848,
|
| 1069 |
+
"eval_runtime": 139.0129,
|
| 1070 |
+
"eval_samples_per_second": 58.8,
|
| 1071 |
+
"eval_steps_per_second": 2.453,
|
| 1072 |
+
"step": 38000
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 7.06,
|
| 1076 |
+
"learning_rate": 4.44703495666965e-05,
|
| 1077 |
+
"loss": 0.2151,
|
| 1078 |
+
"step": 38500
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 7.06,
|
| 1082 |
+
"eval_loss": 0.6073034405708313,
|
| 1083 |
+
"eval_runtime": 139.179,
|
| 1084 |
+
"eval_samples_per_second": 58.73,
|
| 1085 |
+
"eval_steps_per_second": 2.45,
|
| 1086 |
+
"step": 38500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 7.15,
|
| 1090 |
+
"learning_rate": 4.5572824104633835e-05,
|
| 1091 |
+
"loss": 0.222,
|
| 1092 |
+
"step": 39000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 7.15,
|
| 1096 |
+
"eval_loss": 0.5468436479568481,
|
| 1097 |
+
"eval_runtime": 139.1916,
|
| 1098 |
+
"eval_samples_per_second": 58.725,
|
| 1099 |
+
"eval_steps_per_second": 2.45,
|
| 1100 |
+
"step": 39000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 7.25,
|
| 1104 |
+
"learning_rate": 4.656346367280503e-05,
|
| 1105 |
+
"loss": 0.236,
|
| 1106 |
+
"step": 39500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 7.25,
|
| 1110 |
+
"eval_loss": 0.5504103899002075,
|
| 1111 |
+
"eval_runtime": 139.2016,
|
| 1112 |
+
"eval_samples_per_second": 58.721,
|
| 1113 |
+
"eval_steps_per_second": 2.45,
|
| 1114 |
+
"step": 39500
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 7.34,
|
| 1118 |
+
"learning_rate": 4.743688310164889e-05,
|
| 1119 |
+
"loss": 0.2031,
|
| 1120 |
+
"step": 40000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 7.34,
|
| 1124 |
+
"eval_loss": 0.5548919439315796,
|
| 1125 |
+
"eval_runtime": 139.2056,
|
| 1126 |
+
"eval_samples_per_second": 58.719,
|
| 1127 |
+
"eval_steps_per_second": 2.45,
|
| 1128 |
+
"step": 40000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 7.43,
|
| 1132 |
+
"learning_rate": 4.818833443653748e-05,
|
| 1133 |
+
"loss": 0.2251,
|
| 1134 |
+
"step": 40500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 7.43,
|
| 1138 |
+
"eval_loss": 0.5905419588088989,
|
| 1139 |
+
"eval_runtime": 139.1367,
|
| 1140 |
+
"eval_samples_per_second": 58.748,
|
| 1141 |
+
"eval_steps_per_second": 2.451,
|
| 1142 |
+
"step": 40500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 7.52,
|
| 1146 |
+
"learning_rate": 4.881373274791077e-05,
|
| 1147 |
+
"loss": 0.2251,
|
| 1148 |
+
"step": 41000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 7.52,
|
| 1152 |
+
"eval_loss": 0.6011632680892944,
|
| 1153 |
+
"eval_runtime": 139.1129,
|
| 1154 |
+
"eval_samples_per_second": 58.758,
|
| 1155 |
+
"eval_steps_per_second": 2.451,
|
| 1156 |
+
"step": 41000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 7.61,
|
| 1160 |
+
"learning_rate": 4.9309678337171785e-05,
|
| 1161 |
+
"loss": 0.2464,
|
| 1162 |
+
"step": 41500
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 7.61,
|
| 1166 |
+
"eval_loss": 0.5931146740913391,
|
| 1167 |
+
"eval_runtime": 139.1046,
|
| 1168 |
+
"eval_samples_per_second": 58.762,
|
| 1169 |
+
"eval_steps_per_second": 2.451,
|
| 1170 |
+
"step": 41500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 7.71,
|
| 1174 |
+
"learning_rate": 4.9673475217629615e-05,
|
| 1175 |
+
"loss": 0.2451,
|
| 1176 |
+
"step": 42000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 7.71,
|
| 1180 |
+
"eval_loss": 0.6498579978942871,
|
| 1181 |
+
"eval_runtime": 139.0889,
|
| 1182 |
+
"eval_samples_per_second": 58.768,
|
| 1183 |
+
"eval_steps_per_second": 2.452,
|
| 1184 |
+
"step": 42000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 7.8,
|
| 1188 |
+
"learning_rate": 4.990314577002693e-05,
|
| 1189 |
+
"loss": 0.2463,
|
| 1190 |
+
"step": 42500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 7.8,
|
| 1194 |
+
"eval_loss": 0.5696046948432922,
|
| 1195 |
+
"eval_runtime": 139.0384,
|
| 1196 |
+
"eval_samples_per_second": 58.79,
|
| 1197 |
+
"eval_steps_per_second": 2.453,
|
| 1198 |
+
"step": 42500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 7.89,
|
| 1202 |
+
"learning_rate": 4.999744149298381e-05,
|
| 1203 |
+
"loss": 0.2385,
|
| 1204 |
+
"step": 43000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 7.89,
|
| 1208 |
+
"eval_loss": 0.5360204577445984,
|
| 1209 |
+
"eval_runtime": 139.0432,
|
| 1210 |
+
"eval_samples_per_second": 58.787,
|
| 1211 |
+
"eval_steps_per_second": 2.452,
|
| 1212 |
+
"step": 43000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 7.98,
|
| 1216 |
+
"learning_rate": 4.995584978991786e-05,
|
| 1217 |
+
"loss": 0.2353,
|
| 1218 |
+
"step": 43500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 7.98,
|
| 1222 |
+
"eval_loss": 0.5489608645439148,
|
| 1223 |
+
"eval_runtime": 139.1804,
|
| 1224 |
+
"eval_samples_per_second": 58.73,
|
| 1225 |
+
"eval_steps_per_second": 2.45,
|
| 1226 |
+
"step": 43500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 8.0,
|
| 1230 |
+
"step": 43608,
|
| 1231 |
+
"total_flos": 1.5655045448788992e+17,
|
| 1232 |
+
"train_loss": 0.21080181559736064,
|
| 1233 |
+
"train_runtime": 44575.4239,
|
| 1234 |
+
"train_samples_per_second": 11.741,
|
| 1235 |
+
"train_steps_per_second": 0.978
|
| 1236 |
}
|
| 1237 |
],
|
| 1238 |
+
"max_steps": 43608,
|
| 1239 |
+
"num_train_epochs": 8,
|
| 1240 |
+
"total_flos": 1.5655045448788992e+17,
|
| 1241 |
"trial_name": null,
|
| 1242 |
"trial_params": null
|
| 1243 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5774ed6a6ee7d12e490235aaa201c6682bceb991af75ae978177e58f9bbfb1a7
|
| 3 |
+
size 4091
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|